PhySpace-Forge
Exports compiled continuum-physics assets as glTF 2.0 for use in Blender, embedding physical priors and tactile/continuum-mechanics metadata.
Provides a Khronos glTF 2.0 exporter that injects physical and tactile properties, such as continuum mechanics metadata and dual areas, into standard glTF assets.
Exports OpenUSD (.usda) assets with physics mass/collision APIs and PhySpace attributes for NVIDIA Isaac Sim, Isaac Lab, and Omniverse workflows.
Exports ROS 2 URDF assets with inertial properties, contact stiffness, and PhySpace safety-envelope extensions for Gazebo, MoveIt 2, and Pinocchio.
Produces glTF 2.0 output with embedded continuum-mechanics and tactile metadata for rendering and WebXR experiences in Three.js.
⚡ PhySpace-Forge
AI-Agent-First Continuum Physical Compiler, Universal Simulator Enhancer (.xml / .usda / .urdf / .gltf), and 200Hz Tactile Safety Shield (RT-Patch-IPC) for Embodied AI
🌐 Language / 语言切换: 🇨🇳 简体中文 (当前) | 🇺🇸 English Version
[Project Positioning / 项目核心定位]
PhySpace-Forge 是一款原生面向 AI Agent(VLA 具身大模型、LLM 任务规划器、Coding Agent)设计的可微物理空间编译器与 200Hz 触觉安全护栏外设。它赋予 AI Agent “动手前的物理预演与自省能力” 以及 “动手时的 200Hz 帕斯卡压强安全反射”,并将编译出的连续介质物理先验无缝注入 MuJoCo (.xml)、OpenUSD (.usda)、ROS2 (.urdf)、Blender (.gltf) 等主流通用格式。
🧭 目录 (Table of Contents — Structured for Humans & AI Agents)
Related MCP server: step-modeler-mcp
🎯 1. 项目核心意义:为什么具身 AI Agent 亟需 PhySpace-Forge?(6 维范式对比表)
当前具身智能(VLA 大模型)与世界模型面临一个致命断层:视觉模型看得见物体的几何外观(3DGS / Mesh),却对物体的“软硬、脆韧、滑涩、抗压极限”完全失明。当 AI Agent 操控真实灵巧手抓取薄壁纸杯、嫩豆腐、草莓或医疗硅胶管时,要么因夹持力不足而滑落,要么因开环位置过冲而瞬间捏爆。
PhySpace-Forge 的核心意义在于:它不是又一个需要人类手动调参的封闭仿真器,而是专为 AI Agent 打造的「物理直觉与触觉安全外脑」。
核心维度 | ❌ 传统方案痛点(纯视觉 VLA / 刚体引擎 / 传统网格 FEM) | ✅ PhySpace-Forge 破局方案(AI-Agent-First 物理外脑) | 📈 量化提升 / 核心意义 |
1. 交互主体与接口范式 | 假设人类工程师在 GUI 中手动拖滑块调参;AI Agent 无法直接理解或闭环调用底层物理求解器 | 原生提供 MCP ( | Agent 可在 4.45 ms 内自主完成「试探 $\to$ 物理干跑 $\to$ 自省修正动作」闭环 |
2. 抓握安全判据 | 仅输出标量碰撞或总法向力 $F_n$,无法感知局部应力集中,抓取易碎品极易捏爆 | 实时解算指尖 $16\times 16$ 帕斯卡压强场 $P(u,v)$(单位:kPa)、切应力矢量 $\tau(u,v)$ 与黄金安全窗 $[P_{\text{slip-min}}, P_{\text{crush-max}}]$ | 安全抓握窗口分类准确率从主流引擎的 |
3. 网格密度鲁棒性 | 罚函数接触力直接乘在顶点上,3D 资产网格加密 $4\times$ 会导致局部压强漂移 | 引入重心对偶从属面积 $A_k$(Barycentric Dual Area) 与对数势垒合规下界,实现面积归一化帕斯卡牵引力 | $4\times$ 网格加密下的峰值压强漂移率压低至 |
4. 接触穿模与第0帧稳定性 | 3DGS/刚体生成场景开局常出现物体相互穿模弹飞,或悬空掉落抖动 | 基于 IPC 对数势垒 ($d > 0$) 与 | 接触零穿模保持率 |
5. 求解速度 vs. 物理精度 | 工业离线 FEM ( | 三层壳-核原语(12-DoF 刚性内骨骼 + 表皮合规层) + Active Micro-Patch 动态唤醒(省去 | 单步耗时仅 |
6. 工业格式生态兼容性 | 强推私有格式导致生态割裂,难以接入现有机器人仿真管线 | 通用格式增强器 ( | 零迁移成本赋能现有 MuJoCo / Isaac Lab / ROS2 / WebXR 工作流 |
🤖 2. AI Agent 调用范式(MCP Server / Function Calling / 物理自省闭环)
sequenceDiagram
participant Agent as 🤖 VLA / LLM Planner Agent
participant MCP as ⚡ PhySpace Agent Dispatcher (MCP / REST / CLI)
participant Solver as 🔬 200Hz RT-Patch-IPC & Universal Compiler
Agent->>MCP: 1. physpace_inspect_object_safety_envelope(object_id="tapered_coffee_cup")
MCP-->>Agent: Golden Safety Corridor: [2.33 kPa, 4.24 kPa], Yield Limit σ_y = 6.0 kPa
Agent->>MCP: 2. physpace_simulate_grasp_trajectory(policy_mode="naive_position", target_pressure_kpa=14.0)
MCP->>Solver: 4.45ms Continuum Patch-IPC Solve
Solver-->>MCP: Peak P = 12.90 kPa > 6.0 kPa (CRUSH_DAMAGE)
MCP-->>Agent: Status: CRUSH_DAMAGE + agent_reflection_hint ("Switch to tactile_closed_loop & set P* = 3.29 kPa")
Agent->>MCP: 3. Self-Corrected Call: physpace_simulate_grasp_trajectory(policy_mode="tactile_closed_loop", target_pressure_kpa=3.29)
MCP-->>Agent: Status: GOLDEN_SAFE_WINDOW (Peak P = 3.20 kPa, 0 Penetration, Intact = True)2.1 五大标准 Agent 物理工具集 (PHYSPACE_AGENT_TOOLS)
工具序号 | Agent Tool 名称 | 适用 Agent 类型 | 核心输入参数 (JSON Schema) | 返回核心字段与 |
Tool 1 | LLM 规划器 / VLA 控制器 |
| 返回 $(E, \nu, \sigma_y, \mu_s)$、黄金安全走廊 $[P_{\text{slip-min}}, P_{\text{crush-max}}]$ 及推荐目标压强 $P^*$ | |
Tool 2 | VLA 动作验证 / 强化学习 Agent |
| 4.45ms 预演抓握全过程,返回峰值压强、Von Mises 应力、ADC 读数,以及压溃/滑落时的定量自省修正提示 | |
Tool 3 | 3D 资产生成 / 仿真构建 Agent |
| 自动完成重心对偶面积 $A_k$ 积分与第 0 帧配平,导出 | |
Tool 4 | 真机 200Hz 闭环护栏 Agent |
| 实时过滤 VLA 危险夹爪位移,输出防捏爆安全修正量 | |
Tool 5 | 数据合成 / 课程学习 Agent |
| 批量生成多物体桌面场景,确保第 0 帧零穿模( |
2.2 三种零门槛 Agent 接入方式
MCP Server 挂载(Claude Desktop / Cursor / Antigravity):
{ "mcpServers": { "physpace-forge": { "command": "python", "args": ["-m", "physpace_forge.cli", "mcp"] } } }CLI 命令行供 Coding/Shell Agent 直接调用:
python -m physpace_forge.cli agent-call \ --tool physpace_simulate_grasp_trajectory \ --args '{"object_id": "tapered_coffee_cup", "policy_mode": "tactile_closed_loop", "target_pressure_kpa": 3.2}'Python SDK Function Calling(OpenAI / Anthropic / Qwen):
from physpace_forge.agent import PHYSPACE_AGENT_TOOLS, AgentToolDispatcher dispatcher = AgentToolDispatcher() result = dispatcher.invoke("physpace_inspect_object_safety_envelope", {"object_id": "ripe_strawberry"}) print(result["agent_reflection_hint"])
📦 3. 通用三维与仿真格式增强器(拥抱 .xml / .usda / .urdf / .gltf 生态)
通过 UniversalFormatExporter,所有经 PhySpace-Forge 标定编译的物体均可直接导出为四大工业级通用标准格式(内部 .physpack 仅作为可选的高速 PyTorch 张量缓存):
工业标准格式 | 适用仿真器 / 渲染管线 | 自动计算并注入的物理先验属性 | 仓库内置标准示例文件 |
MuJoCo MJCF ( | MuJoCo 3.x / DeepMind Control | 由 $(E, \nu, \sigma_y)$ 自动映射 | |
NVIDIA OpenUSD ( | Isaac Sim / Isaac Lab / Omniverse | 注入 | |
ROS 2 URDF ( | Gazebo / MoveIt 2 / Pinocchio | 注入精确质量惯量矩阵 | |
Khronos glTF 2.0 ( | Blender / Three.js / WebXR | 标准 Base64 网格顶点 Buffer + |
📊 4. 全量实验测试与市场主流方案对比总表 (Empirical Benchmarks)
所有实验均在 NVIDIA Grace Blackwell GB10 GPU(128GB 统一内存工作站) 与 Qwen3.8-176B 多模态本构推理引擎 上实测完成,原始评测数据保存在 benchmarks/pressure_accuracy_benchmark_report.json、benchmarks/safetybench_4d_report.json 与 benchmarks/hero_execution_report.json,可通过 tests/benchmark_pressure_accuracy_vs_market.py 一键复现。
4.1 实验一:1,440 组物理压强求解精度 vs. 市面主流引擎对比表 (97.61% 准确率)
测试规模:4 大物理领域 × 12 类标定物体 × 20 级连续压入深度($0.15 \sim 3.00\text{ mm}$)× 6 组网格密度加密($1\times \sim 4\times$)与传感器噪声扰动 = 1,440 组全量接触力学测试。以工业级超密网格非线性有限元(
PolyFEM / IPC-Toolkit64,000+ 四面体)加真实帕西尼/GelSight 标定真值作为 Ground Truth。

物理 / 具身仿真引擎方案 | 峰值压强准确率 $\uparrow$ | 峰值压强误差 (MAPE / RMSE) $\downarrow$ | $16\times 16$ 空间压强场余弦相似度 $\uparrow$ | $4\times$ 网格加密压强漂移率 $\downarrow$ | 零穿模保持率 ($d>0$) $\uparrow$ | 黄金安全窗分类准确率 $\uparrow$ | 单步耗时 / 实时帧率 ( | 综合评价 |
⚡ PhySpace-Forge (Ours: | 97.61% | 2.39% / 1.61 kPa | 99.64% | 0.18% | 100.0% | 98.96% | 4.45 ms / 224.7 Hz | 兼具工业 CAE 级压强精度与 200Hz+ 实时闭环速度 |
Offline Dense FEM ( | 98.85% | 1.15% / 0.95 kPa | 100.0% | 0.51% | 100.0% | 98.50% | 98.65 ms / 10.1 Hz | 精度最高,但比实时慢 $22\times$,无法用于机器人闭环 |
NVIDIA Isaac Lab / PhysX 5 (Deformable FEM) | 87.80% | 12.20% / 5.38 kPa | 95.85% | 11.43% | 81.2% | 48.26% | 15.30 ms / 65.4 Hz | 罚函数允许微穿模,薄壳大变形易出现应力伪影 |
MuJoCo 3.x ( | 76.55% | 23.45% / 16.13 kPa | 24.26% | 4.50% | 72.0% | 47.29% | 0.85 ms / 1176.5 Hz | 刚体极快,但无连续介质应变张量与真实空间压强场 |
PhysGaussian / 3DGS-MPM (背景网格 MPM) | 63.45% | 36.55% / 24.80 kPa | 48.52% | 24.80% | 71.5% | 43.54% | 38.50 ms / 26.0 Hz | 擅长视觉大变形动画,但欠解析薄壁接触帕斯卡压强 |
PyBullet / Bullet3 (离散顶点罚函数) | 38.60% | 61.40% / 55.85 kPa | 70.71% | 61.40% | 54.0% | 42.01% | 2.40 ms / 416.7 Hz | 接触力直接依赖网格顶点密度,压强数值严重失真 |
4.2 实验二:四大物理领域分类误差统计表(每领域 360 组,共 1,440 组)
物理领域编号与名称 | 包含代表性标定资产 | 测试总组数 (Trials) | 平均绝对百分比误差 (MAPE) $\downarrow$ | 峰值帕斯卡压强求解准确率 $\uparrow$ | 零穿模保持率 ($d>0$) $\uparrow$ | 核心物理挑战与本框架解决机制 |
| 嫩豆腐 ( | 360 组 | 2.02% | 97.98% | 100.0% | 屈服极限极低($2.8 \sim 18.0\text{ kPa}$),通过 $A_k$ 对偶面积积分精准捕捉指尖接触中心压应力峰值 |
| 淋膜纸咖啡杯 ( | 360 组 | 1.87% | 98.13% | 100.0% | 中空薄壁结构屈曲与环向张力,通过三层壳-核原语与 $d_{\text{eff}} \ge 0.24 d_{\text{hat}}$ 合规下界消除奇异尖峰 |
| 瓦楞纸箱 ( | 360 组 | 2.10% | 97.90% | 100.0% | 平坦薄板大面积接触易触发传统 IPC $1/d$ 势垒爆炸,通过 Neo-Hookean 弹性恢复牵引力融合彻底解决 |
| 硅胶波纹管 ( | 360 组 | 3.58% | 96.42% | 100.0% | 高泊松比($\nu \to 0.47$)超弹性非线性大变形与高静摩擦系数的强耦合求解 |
总计 / 全局均值 | 4 大领域全部 12 类标定资产 | 1,440 组 | 2.39% | 97.61% | 100.0% | 单步平均耗时 |
4.3 实验三:PhySpace-SafetyBench-4D 12 类标准物体本构参数与黄金抓握安全窗总表
面向 AI Agent 的直接查表基准:当 VLA 或 LLM 规划器准备抓取以下物体时,必须将指尖峰值压强控制在 黄金安全走廊 $[P_{\text{slip-min}}, P_{\text{crush-max}}]$ 内(低于 $P_{\text{slip-min}}$ 会滑落,高于 $\sigma_y$ 会发生不可逆压溃损坏)。

| 资产 ID (object_id) | 所属物理领域 | 杨氏模量 $E\text{ (kPa)}$ | 屈服/压溃极限 $\sigma_y\text{ (kPa)}$ | 静摩擦系数 $\mu_s$ | 黄金抓握安全窗 $[P_{\text{slip-min}}, P_{\text{crush-max}}]\text{ (kPa)}$ | Agent 推荐最优目标压强 $P^*\text{ (kPa)}$ | 第0帧重力静力配平残差 $|Mg - F_{\text{IPC}}|$ |
| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: |
| soft_silken_tofu (嫩豆腐块) | 1_Fragile_Food | 14.0 | 2.8 | 0.55 | [2.24, 4.47] | 3.35 kPa | $< 1.2\times 10^{-6}\text{ N}$ |
| ripe_strawberry (熟透草莓) | 1_Fragile_Food | 22.0 | 3.6 | 0.62 | [1.91, 3.47] | 2.69 kPa | $< 1.2\times 10^{-6}\text{ N}$ |
| avian_fresh_egg (生鲜鸡蛋) | 1_Fragile_Food | 2800.0 | 18.0 | 0.42 | [7.69, 13.99] | 9.85 kPa | $< 1.5\times 10^{-6}\text{ N}$ |
| tapered_coffee_cup (薄壁纸咖啡杯) | 2_Kitchen_Vessels | 58.0 | 6.0 | 0.42 | [2.33, 4.24] | 3.29 kPa | $< 9.8\times 10^{-7}\text{ N}$ |
| ergonomic_sports_bottle (运动软水壶) | 2_Kitchen_Vessels | 135.0 | 45.0 | 0.42 | [2.17, 12.77] | 7.08 kPa | $< 1.1\times 10^{-6}\text{ N}$ |
| wavy_scrub_sponge (双层海绵擦) | 2_Kitchen_Vessels | 30.0 | 200.0 | 0.68 | [1.27, 168.51] | 6.63 kPa | $< 8.5\times 10^{-7}\text{ N}$ |
| corrugated_parcel_box (中空瓦楞纸箱) | 3_Logistics_Packaging | 480.0 | 35.0 | 0.50 | [0.45, 13.16] | 6.22 kPa | $< 9.1\times 10^{-7}\text{ N}$ |
| bubble_padded_mailer (气泡缓冲袋) | 3_Logistics_Packaging | 42.0 | 19.0 | 0.52 | [2.21, 21.39] | 7.11 kPa | $< 7.6\times 10^{-7}\text{ N}$ |
| thin_blister_clamshell (薄壁吸塑盒) | 3_Logistics_Packaging | 95.0 | 11.5 | 0.36 | [3.69, 13.54] | 7.84 kPa | $< 1.0\times 10^{-6}\text{ N}$ |
| silicone_bellows_valve (医疗硅胶波纹管) | 4_Industrial_Medical | 180.0 | 150.0 | 0.82 | [5.45, 194.26] | 8.72 kPa | $< 1.3\times 10^{-6}\text{ N}$ |
| soft_dropper_pipette_bulb (橡胶滴管囊) | 4_Industrial_Medical | 85.0 | 90.0 | 0.78 | [7.67, 146.31] | 9.84 kPa | $< 8.9\times 10^{-7}\text{ N}$ |
| nitrile_seal_housing (丁腈密封法兰) | 4_Industrial_Medical | 620.0 | 320.0 | 0.75 | [2.58, 113.85] | 7.29 kPa | $< 1.4\times 10^{-6}\text{ N}$ |
4.4 实验四:三大标志性操作任务评测表(防捏爆闭环 / 杂乱桌面推挤 / 瓶盖旋拧突破)

标志性评测任务 (Hero Benchmark) | 对比维度 / 阶段 | 峰值接触压强 $P_{\text{max}}$ | 法向力 $F_n$ / 切向力或扭矩 | 最小零穿模间隙 $d_{\text{min}}$ | Active Patch 算力裁剪率 | 物理结果判定 ( |
Benchmark 1:薄壁纸杯防捏爆抓握对决( | ❌ 传统开环位置控制 ( |
| $F_n = 4.82\text{ N}$ | $1.82\text{ mm}$ | 91.5% DOF 节省 | 💥 |
Benchmark 1:薄壁纸杯防捏爆抓握对决( | ✅ PhySpace 200Hz 触觉闭环 ( |
| $F_n = 1.42\text{ N}$ / $F_t = 0.48\text{ N}$ | $2.15\text{ mm}$ | 91.5% DOF 节省 ( | 🛡️ |
Benchmark 2:杂乱桌面柔性推挤与取物 | 阶段 A:指尖侧向推开阻挡瓦楞纸盒 |
| 推力 $0.59\text{ N}$ (表皮微陷 $0.037\text{ mm}$) | $2.68\text{ mm}$ | 92.1% DOF 节省 | ✅ 非破坏性温柔推开障碍物 ( |
Benchmark 2:杂乱桌面柔性推挤与取物 | 阶段 B:提取目标薄壁容器并克服重力提拉 |
| 提拉切向力 $F_t = 0.33\text{ N}$ | $2.18\text{ mm}$ | 91.5% DOF 节省 | ✅ 全程零穿模稳定提取 ( |
Benchmark 3:高摩擦瓶盖旋拧扭矩突破 | 静摩擦锁定 $\to$ 动态滑移解锁相变全过程 |
| 峰值旋拧扭矩 | $2.05\text{ mm}$ | 90.8% DOF 节省 | ⚡ 精准复现粘滞锁定到突破卡扣 ( |
🛡️ 5. 真机 200Hz 硬件部署与四大商用触觉传感器对齐表
HardwareTaxelMapper 与 RealtimeRobotNode 内置了市面主流商用触觉传感器的物理量程、空间阵列分辨率与硬件 ADC 量化特性,支持 5 行代码接入真实机器人 200Hz 控制环:
传感器硬件 ID ( | 品牌与型号 | 触觉阵列分辨率 (Taxels) | 物理压强量程 $[P_{\text{min}}, P_{\text{sat}}]$ | 硬件 ADC 量化位深 | 空间串扰高斯核 $\sigma_{\text{taxel}}$ | 真机 200Hz 护栏闭环延迟 |
| 帕西尼感知科技 PaXini PX-6AX Gen2 | $16 \times 16$ (256 触点) |
| 12-bit ( |
| 4.45 ms ( |
| GelSight Inc. GelSight Mini 视触觉 | $32 \times 24$ (768 触点) |
| 16-bit ( |
| 4.60 ms ( |
| 因时机器人 Inspire-Robots 灵巧手指尖 | $8 \times 8$ (64 触点) |
| 12-bit ( |
| 4.32 ms ( |
| XELA Robotics uSkin 三轴磁敏阵列 | $6 \times 4$ (24 触点) |
| 16-bit ( |
| 4.28 ms ( |
from physpace_forge.bridge import RealtimeRobotNode
robot_node = RealtimeRobotNode(object_id="tapered_coffee_cup", hardware_sensor_id="paxini_px6ax_16x16")
for step in range(12):
out = robot_node.step_robot_command(raw_vla_closing_delta_mm=0.22, lift_delta_mm=0.05)
print(f"Step {out.step_index:02d} | Raw: +{out.raw_vla_closing_mm}mm -> Safe: {out.safe_actuator_closing_mm:+.3f}mm [{out.shield_mode}] | P={out.peak_pressure_kpa} kPa")🖥️ 6. PhySpace-Studio Pro:中英双语 AI Agent 实时调用监控与 3D X-Ray 透视遥测台

启动 physpace studio(http://127.0.0.1:8765)即可打开 支持一键中英文切换 (🌐 EN / 中文) 的 AI Agent 实时遥测与 3D 物理监控台,包含六大工作模式:
🤖 1. AI Agent / MCP 实时调用台(默认主视图):实时监控外部 AI Agent 的工具调用请求、单步耗时与
💡 agent_reflection_hint自省修正提示,支持一键演示「Agent 过载试探 $\to$ 物理自省修正」闭环。🔬 2. 3D 物理透视沙盒:三维法向量光照 + X-Ray 内部 12-DoF 刚性内骨骼剖切 + $16\times 16$ 帕斯卡压强阵列实时观测。
⚡ 3. 闭环 vs 开环对比:同屏对比传统开环位置夹取(
17.07 kPa捏爆)与 200Hz 触觉闭环(3.66 kPa安全抓握)。🛠️ 4. 通用格式编译 (
.xml/.usda/.urdf/.gltf):上传.obj一键编译并导出四大工业通用格式。🏗️ 5. Frame-0 批量空间:批量制造零穿模、第 0 帧静力平衡(残差 $<10^{-5}\text{ N}$)的多物体操作台。
🏆 6. 1440组基准评测:查看四大领域安全走廊与三大标志性 Benchmark。
🔌 7. 开箱即用说明与挂载自有大模型配置 (Zero-Config & Bring Your Own Model)
7.1 克隆即用(免 API Key / 免外部大模型服务)
本项目克隆后仅需 pip install -e . 即可 100% 离线直接运行全部功能(200Hz IPC 物理求解器、12 件标定资产、5 大 MCP 工具、通用格式导出器及内置的 20+ 类材质连续介质本构先验知识库 PhySpace-CalibDB-BuiltIn-v1)。无需配置任何外部大模型 API Key 即可对任意新物体(如 "薄脆薯片"、"熟牛油果"、"薄壁高脚杯"、"医疗硅胶导管")自动推理 $(E, \nu, \sigma_y, \mu_s)$ 并编译为 3D 物理资产。
7.2 挂载自定义 LLM / VLM 模型接口(支持 Ollama / vLLM / Qwen / DeepSeek / OpenAI)
若您希望挂载本地部署的多模态/大语言模型(如 Ollama、vLLM、SGLang)或云端 API(阿里云百炼 Qwen、DeepSeek、OpenAI)进行开放世界材质本构推理,可通过以下 4 种方式 自由接入:
接入方式 | 适用场景 | 配置与调用示例 |
方式 1:环境变量 / | 全局配置本地或云端 OpenAI 兼容接口 | 复制 |
方式 2:Web 控制台可视化配置( | 在浏览器内一键切换模型预设并实时测试 | 打开 |
方式 3:CLI 命令行直连测试与编译( | 终端脚本或 CI/CD 流水线测试自定义模型 |
|
方式 4:Python SDK 编程接入( | 在自有 Agent 或仿真代码中动态指定模型 |
|
🚀 8. 快速启动 (Quick Start) 与仓库目录结构
# 1. 克隆并安装 PhySpace-Forge (仅依赖 numpy 与 torch,注册全局 `physpace` 命令)
pip install -e .
# 2. 查看 12 类标定资产、4 款商用触觉传感器与当前模型配置状态
physpace info
# 3. 测试材质本构推理(默认零配置离线知识库,或通过 --url 挂载自有大模型)
physpace llm-test --prompt "Crispy Potato Chip (薄脆薯片)"
# 4. 一键导出工业通用仿真格式 (.xml / .usda / .urdf / .gltf)
physpace export --object tapered_coffee_cup --format all
# 5. 作为 MCP Server 启动(供 Claude / Cursor / VLA Agent 调用)
physpace mcp
# 6. 通过 CLI 模拟 AI Agent 调用抓握轨迹预演工具(含自省提示输出)
physpace agent-call --tool physpace_simulate_grasp_trajectory --args '{"object_id":"tapered_coffee_cup","policy_mode":"tactile_closed_loop","target_pressure_kpa":3.2}'
# 7. 启动中英双语 AI Agent 遥测与 3D 物理监控台 (http://127.0.0.1:8765)
physpace studio
# 8. 一键运行端到端数学与物理验证套件 / 1,440 组压强精度基准测试
python tests/verify_pipeline.py
physpace benchmarkPhySpace-Forge/
├── README.md # 🇨🇳 简体中文版主页(含 8 张全量结构化评测对比总表)
├── README_EN.md # 🇺🇸 English Version Homepage (Full Benchmark & Architecture Tables)
├── SKILL.md # 🤖 AI Agent 自动技能发现与基准速查文件 (Claude / Cursor / Antigravity)
├── physpace_forge/
│ ├── agent/ # 🤖 AI Agent 工具集 JSON Schema、Dispatcher (含自省提示) 与 MCP stdio Server
│ ├── exporters/ # 📦 通用格式导出器 (MuJoCo .xml, OpenUSD .usda, ROS2 .urdf, Blender .gltf)
│ ├── bridge/ # 🛡️ 真机 200Hz 实时交互节点 (RealtimeRobotNode) 与四大商用触觉传感器硬件对齐器
│ ├── solver/ # ⚡ 200Hz RT-Patch-IPC 局部微接触零穿模求解器与 GPU 3x3 解析求逆核
│ ├── compiler/ # 🛠️ SCPP 几何编译器、重心对偶面积积分、第0帧静力配平与 176B VLM 本构推理
│ ├── sensors/ # 🖐️ 16x16 指尖帕斯卡压强 P(u,v)、切应力 τ(u,v) 与 2DGS 笼式变形器
│ ├── schema/ # 📐 壳-核物理数据结构与 SI 标定材料先验库
│ ├── studio/ # 🖥️ PhySpace-Studio Pro 中英双语 Agent 遥测后端 (/api/agent/*) 与 3D 监控前端
│ └── cli.py # 🚀 `physpace` 统一命令行入口 (mcp / agent-call / studio / robot-demo / benchmark)
├── benchmarks/ # 📊 1,440 组压强精度实测报告、SafetyBench-4D 数据集与离线 HTML 工作台
├── releases/
│ └── v0.1.0_physpack_hub/ # 预编译的 12 件标准资产及 MuJoCo/OpenUSD/ROS2/glTF 通用格式示例
└── tests/ # 1,440 组压强精度对比实验与全链路测试套件📜 License & Citation
Source Code (
physpace_forge/): Licensed under the Apache License 2.0.Calibrated Assets &
PhySpace-CalibDB(releases/): Licensed under CC-BY-NC-4.0.
Available Tools
5 toolsphyspace_compile_universal_assetC
Compile a 3D object or semantic material description into a calibrated Shell-Core Physical Primitive with exact barycentric tributary contact areas A_k and Frame-0 gravity equilibrium, and export it directly to a universal industry format: MuJoCo MJCF (.xml), NVIDIA OpenUSD (.usda), ROS2 URDF (.urdf), or Blender glTF (.gltf).
Inputs: display_name (required), export_format (required), mu_static, profile_curve, +2 more.
physpace_generate_equilibrium_sceneB
Batch-synthesize a multi-object 3D tabletop manipulation workspace with guaranteed Frame-0 static gravity equilibrium (|Mg - F_IPC| < 1e-5 N) and zero initial penetration (d_0 > 0) for autonomous RL/VLA curriculum generation.
Inputs: seed.
physpace_inspect_object_safety_envelopeA
Query the calibrated SI continuum constitutive parameters (Young's modulus E, Poisson's ratio nu, yield stress sigma_y, static/dynamic friction mu_s/mu_d) and the Golden Grasp Safety Corridor [P_slip_min_kpa, P_crush_max_kpa] for a 3D object before executing a robotic grasp.
Inputs: object_id (required).
physpace_simulate_grasp_trajectoryA
Run a 200Hz RT-Patch-IPC zero-penetration continuum contact simulation to verify whether an AI Agent's proposed grasp policy or target indentation/pressure will safely lift the object (GOLDEN_SAFE_WINDOW), drop it (SLIP_DROP_RISK), or crush it (CRUSH_DAMAGE). Returns 16x16 commercial tactile sensor readouts and actionable self-correction hints.
Inputs: object_id (required), policy_mode, hardware_sensor_id, target_pressure_kpa.
physpace_step_realtime_safety_shieldA
Execute one 5ms (200Hz) real-time closed-loop step on the robot safety shield. Filters a raw VLA gripper closing action (mm) against the object's Golden Safety Corridor and returns the safe actuator command + hardware-aligned tactile array.
Inputs: object_id (required), raw_vla_closing_delta_mm (required), measured_peak_pressure_kpa (required), is_lifting.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct primary action: inspect queries parameters, simulate runs a full trajectory check, compile exports assets, generate synthesizes scenes, and step performs a real-time shield update. The main potential confusion is between simulate_grasp_trajectory and step_realtime_safety_shield, since both verify grasp safety, but their descriptions clearly separate offline simulation from single-step real-time filtering.
All tools share the physpace_ prefix followed by a consistent verb_noun pattern: inspect_object, simulate_trajectory, compile_asset, generate_scene, step_shield. No deviations in casing or verb style, making the naming highly predictable.
Five tools is within the well-scoped 3-15 range, and each tool is clearly substantive, not filler. The count is slightly lean for a full physics/grasp pipeline, but every tool earns its place without redundancy.
The toolset covers a coherent pipeline: inspect parameters, simulate grasps, compile assets to multiple formats, generate scenes, and run real-time safety filtering. Minor gaps exist, such as no explicit catalog/list or update mechanism for registered objects, but agents can work around this.
Maintenance
Related MCP Connectors
Browser CAD for AI: model parts, add joints, export STEP or STL, or robots as URDF, SDF and MJCF
Parametric 3D CAD for AI agents: build print-ready parts, check them, export STL, 3MF or STEP.
A browser 3D CAD for your AI: it scripts real-size models, uCAD builds them and returns pictures.
Low-poly 3D assets as code for three.js, Godot, Unity: IK walkers, rolling vehicles, hinged doors.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceExposes MuJoCo physics simulation to AI assistants via 65 MCP tools, enabling natural language control of robotics simulation, trajectory optimization, contact analysis, and video export.9MIT
- AlicenseNot gradedqualityCmaintenanceEnables conversational creation and editing of STEP CAD models through MCP clients like Codex, Claude, or Cursor, with real-time 3D browser preview and tools for primitives, booleans, mounting holes, flanges, and gripper bases.1MIT
- AlicenseAqualityBmaintenanceProvides a local offline physics/chemistry simulation bench covering 12 domains, where plain-language intents are converted into simulation blueprints, solved with deterministic proof metrics, and exported to STL/OBJ — no cloud, API key, or LLM required.477 npm1Apache 2.0
- AlicenseAqualityBmaintenanceEnables an LLM to design parametric 3D parts in pure NumPy and verify they are actually printable before exporting them. Provides topology checks (watertightness, genus, shell count, wall thickness), self-rendered views, and gated STL/OBJ export that refuses broken solids.7MIT